Abstract: Counting and detecting the pedestrians is an important and critical aspect for several applications such as estimation of crowd density, organization of events, individual’s flow control, and surveillance systems to prevent the difficulties and overcrowding in a huge gathering of pedestrians such as the Hajj occasion, which is the annual event for Muslims with the growing number of pilgrims every year. This paper is based on applying some enhancements to two different techniques for automatically estimating the crowd density. These two approaches are based on individual motion and the body’s thermal features. Theessential characteristic of crowd counting techniques is that they do not require a previously stored and trained data; instead they use a live video stream as input. Also, it does not require any intervention from individuals. So, this feature makes it easy to automatically estimate the crowd density. What makes this work special than other approaches in literature is the use of thermal videos, and not just relying on a way or combining several ways to get the crowd size but also analyzing the results to decide which approach is better considering different cases of scenes. This work aims at estimating the crowd density using two methods and decide which method is better and more accurate depending on the case of the scene; i.e., this work measures the crowd size from videos using the heat signature and motion analysis of the human body, plus using the results analysis of both approaches to decide which approach is better. The better approach can vary from video-to-video according to many factors such as the motion state of humans in this video, the occlusion amount, etc. Both approaches are discussed in this paper. The first one is based on capturing the thermal features of an individual and the second one is based on detecting the features of an individual motion. The result of these approaches has been discussed, and different experiments were conducted to prove and identify the most accurate approach. The experimental results prove the advancement of the approach proposed in this paper over the literature as indicated in the result section. PubDate: Thu, 01 Dec 2022 14:20:00 +000
Abstract: A recommender system is an information selection system that offers preferences to users and enhances their decision-making. This system is commonly implemented in human-computer-interaction (HCI) intervention because of its information filtering and personalization. However, its success rate in decision-making intervention is considered low and the rationale for this is associated with users’ psychological reactance which is causing unsuccessful recommender system interventions. This paper employs a computational model to depict factors that lead to recommender system rejection by users and how these factors can be enhanced to achieve successful recommender system interventions. The study made use of design science research methodology by executing a computational analysis based on an agent-based simulation approach for the model development and implementation. A total of sixteen model concepts were identified and formalized which were implemented in a Matlab environment using three major case conditions as suggested in previous studies. The result of the study provides an explicit comprehension on interplaying of recommender system that generate psychological reactance which is of great importance to recommender system developers and designers to depict how successful recommender system interventions can be achieved without users experiencing reactance and rejection on the system. PubDate: Thu, 01 Dec 2022 10:20:00 +000
Abstract: This paper presents a new heuristic method for maximum power point tracking (MPPT) in PV systems under normal and shadowing situations. The proposed method is a modification of the original queen honey bee migration (QHBM) to shorten the computation time for the maximum power point (MPP) in PV systems. QHBM initially uses random target locations to search for targets, in this case, MPP. So, we adjusted it to be able to do MPP point quests quickly. We accelerated the mQHBM learning process from the original randomly. We had fairly compared the mQHBM with several heuristics. Simulations were carried out with 2 scenarios to test the mQHBM. Based on the simulation results, it was found that mQHBM was able to exceed the capabilities of other methods such as original QHBM, particle swarm optimization (PSO) and perturb and observe (P&O), ANN, gray wolf (GWO), and cuckoo search (CS) in terms of MPPT speed and overshoot. However, the accuracy of mQHBM cannot exceed QHBM, ANN, and GWO. But still, mQHBM is better than PSO and P&O by about 15% and 18%, respectively. This experiment resulted in a gap of about 2% faster in speed, 0.34 seconds better in convergence time, and 0.2 fewer accuracies. PubDate: Sat, 26 Nov 2022 05:20:02 +000
Abstract: The Maximum Lifetime Coverage Problem (MLCP) requires heuristic optimization methods due to its complexity. A real-world problem model determines how a solution is represented and the operators applied in these heuristics. Our paper describes adapting a local search scheme and its operators to MLCP optimization. The operators originate from three local search algorithms we proposed earlier: LSHMA, LSCAIA, and LSRFTA. Two steps of the LS scheme’s main loop can be executed in three different ways each. Hence, nine versions of the LS approach can be obtained. In experimental research, we verified their effectiveness. Test cases come from three benchmarks: SCP1, proposed and used in our earlier research on the three LS algorithms mentioned above, and two others found in the literature. The results obtained with SCP1 showed that the algorithm based on the hypergraph model approach (HMA) is the most effective. The remaining results of the other algorithms divide them into two groups: effective ones and weak ones. However, other benchmarks showed that the more redundant the coverage of points of interest (POIs) by sensors, the more effective the perturbation method from the approach inspired by cellular automata (CAIA). The findings expose the strengths and weaknesses of the problem-specific steps applied in the LS algorithms. PubDate: Sat, 12 Nov 2022 05:05:01 +000
Abstract: Amharic language is the second most spoken language in the Semitic family after Arabic. In Ethiopia and neighboring countries more than 100 million people speak the Amharic language. There are many historical documents that are written using the Geez script. Digitizing historical handwritten documents and recognizing handwritten characters is essential to preserving valuable documents. Handwritten digit recognition is one of the tasks of digitizing handwritten documents from different sources. Currently, handwritten Geez digit recognition researches are very few, and there is no available organized dataset for the public researchers. Convolutional neural network (CNN) is preferable for pattern recognition like in handwritten document recognition by extracting a feature from different styles of writing. In this work, the proposed model is to recognize Geez digits using CNN. Deep neural networks, which have recently shown exceptional performance in numerous pattern recognition and machine learning applications, are used to recognize handwritten Geez digits, but this has not been attempted for Ethiopic scripts. Our dataset, which contains 51,952 images of handwritten Geez digits collected from 524 individuals, is used to train and evaluate the CNN model. The application of the CNN improves the performance of several machine-learning classification methods significantly. Our proposed CNN model has an accuracy of 96.21% and a loss of 0.2013. In comparison to earlier research works on Geez handwritten digit recognition, the study was able to attain higher recognition accuracy using the developed CNN model. PubDate: Tue, 08 Nov 2022 06:50:02 +000
Abstract: This article is the first step to formulate such higher dimensional mathematical structures in the extended fuzzy set theory that includes time as a fundamental source of variation. To deal with such higher dimensional information, some modern data processing structures had to be built. Classical matrices (connecting equations and variables through rows and columns) are a limited approach to organizing higher dimensional data, composed of scattered information in numerous forms and vague appearances that differ on time levels. To extend the approach of organizing and classifying the higher dimensional information in terms of specific time levels, this unique plithogenic crisp time-leveled hypersoft-matrix (PCTLHS matrix) model is introduced. This hypersoft matrix has multiple parallel layers that describe parallel universes/realities/information on some specific time levels as a combined view of events. Furthermore, a specific kind of view of the matrix is described as a top view. According to this view, i-level cuts, sublevel cuts, and sub-sublevel cuts are introduced. These level cuts sort the clusters of information initially, subject-wise then attribute-wise, and finally time-wise. These level cuts are such matrix layers that focus on one required piece of information while allowing the variation of others, which is like viewing higher dimensional images in lower dimensions as a single layer of the PCTLHS matrix. In addition, some local aggregation operators are designed to unify i-level cuts. These local operators serve the purpose of unifying the material bodies of the universe. This means that all elements of the universe are fused and represented as a single body of matter, reflecting multiple attributes on different time planes. This is how the concept of a unified global matter (something like dark matter) is visualized. Finally, to describe the model in detail, a numerical example is constructed to organize and classify the states of patients with COVID-19. PubDate: Tue, 01 Nov 2022 09:35:01 +000
Abstract: Because of numerous dormant application fields, wireless sensor networks (WSNs) have emerged as an important and novel area in radio and mobile computing research. These applications range from enclosed system configurations in the home and office to alfresco enlistment in an opponent’s landmass in a strategic flashpoint. Cognitive radio networks (CRNs) can be created by integrating radio link capabilities with network layer operations utilizing cognitive radios. The goal of CRN design is to optimize the general system operations to meet customer requirements at any location worldwide by much more efficiently addressing CRNs instead of simply connecting spectrum utilization. When compared to conventional radio networks, CRNs are more versatile and susceptible to wireless connections. Recent advancements in wireless communication have resulted in increasing spectrum scarcity. As a modern innovation, cognitive radio aims to tackle this challenge by proactively utilizing the spectrum. Because cognitive radio (CR) technology gives assailants additional possibilities than a normal wireless network, privacy in a CRN becomes a difficult challenge. We concentrate on examining the surveillance system at a societal level, in which both defense and monitoring are critical components in assuring the channel’s privacy. The current state of investigation into spectrum sensing and potential risks in cognitive radios is reviewed in this study. PubDate: Sun, 30 Oct 2022 04:05:02 +000
Abstract: Gestational diabetes is a type of high blood sugar that develops during pregnancy. It can occur at any stage of pregnancy and cause problems for both the mother and the baby, during and after birth. The risks can be reduced if they are early detected and managed, especially in areas where only periodic tests of pregnant women are available. Intelligent systems designed by machine learning algorithms are remodelling all fields of our lives, including the healthcare system. This study proposes a combined prediction model to diagnose gestational diabetes. The dataset was obtained from the Kurdistan region laboratories, which collected information from pregnant women with and without diabetes. The suggested model uses the clustering KMeans technique for data reduction and the elbow method to find the optimal k value and the Mahalanobis distance method to find more related cluster to new samples, and the classification methods such as decision tree, random forest, SVM, KNN, logistic regression, and Naïve Bayes are used for prediction. The results showed that using a mix of KMeans clustering, elbow method, Mahalanobis distance, and ensemble technique significantly improves prediction accuracy. PubDate: Sat, 22 Oct 2022 09:20:01 +000
Abstract: Since the commercialization of agriculture technology, there has been a surge in interest in agricultural data. However, these data are notoriously chaotic, and analysts are concerned about their authenticity because there is a big possibility that others may have influenced data quality at various points along the data stream. This article suggests a new blockchain architecture to protect the integrity of agricultural data. The goal of this architecture is to provide farmers with safe storage. The agriculture data inserted cannot be modified without some rules. Many procedures are completed automatically using smart contracts to limit the danger of manipulation. One of the suggested architectures is the proof of concept. It connects a traditional farm system with the blockchain accompanied by smart contracts to facilitate the entire agri-supply chain. The conceptual architecture will eliminate the flaws discovered in prior studies. Sensors are used in this approach to provide us with environmental data. As a result, we store our data in blocks using the blockchain system. Then, we built some unique agricultural smart contracts to handle all transactions and automatize decisions based on the source code of these automated contracts. This strategy would be more efficient and secure. PubDate: Fri, 21 Oct 2022 08:35:01 +000
Abstract: Novel coronavirus (COVID-19) is a new strain of coronavirus, first identified in a cluster with pneumonia symptoms caused by SARS-CoV-2 virus. It is fast spreading all over the world. Most infected people will develop mild to moderate illness and recover without hospitalization. Currently, real-time quantitative reverse transcription-PCR (rqRT-PCR) is popular for coronavirus detection due to its high specificity, simple quantitative analysis, and higher sensitivity than conventional RT-PCR. Antigen tests are also commonly used. It is very essential for the automatic detection of COVID-19 from publicly available resources. Chest X-ray (CXR) images are used for the classification of COVID-19, normal, and viral pneumonia cases. The CXR images are divided into sub-blocks for finding out the discrete cosine transform (DCT) for every sub-block in this proposed method. In order to produce a compressed version for each CXR image, the DCT energy compaction capability is used. For each image, hardly few spectral DCT components are included as features. The dimension of the final feature vectors is reduced by scanning the compressed images using average pooling windows. In the 3-set classification, a multilayer artificial neural network is used. It is essential to triage non-COVID-19 patients with pneumonia to give out hospital resources efficiently. Higher size feature vectors are used for designing binary classification for COVID-19 and pneumonia. The proposed method achieved an average accuracy of 95% and 94% for the 3-set classification and binary classification, respectively. The proposed method achieves better accuracy than that of the recent state-of-the-art techniques. Also, the time required for the implementation is less. PubDate: Thu, 20 Oct 2022 05:35:00 +000
Abstract: Alzheimer’s disease (AD) is a progressive and fatal disease, due to the nonavailability of any permanent cure. Some treatments are under experimentation that can slow down and possibly pause the progression of the disease only if the disease is diagnosed earlier. The onset of AD can only be detected at the mild cognitive impairment (MCI) stage in which slight memory loss is observed but daily routine functions are intact. A small fraction of the patient progresses from MCI to AD. In this research, we have designed a cascaded deep neural network model to identify those MCI subjects who will progress to AD in the following year. The analysis and experimentation have been performed using twenty longitudinal neuropsychological measures (NMs) provided by Alzheimer’s Disease Neuroimaging Initiative (ADNI). After normalization and ranking of longitudinal data, the deep neural network regression model is trained and tuned to forecast the next in-sequence biomarker value using two previous follow-up readings for each marker. Then, the three time-domain window samples are fed into another deep neural network classifier model for the classification of MCI progressor (MCIp) and MCI stables (MCIs). Our model presented regression forecasting MAE of 0.13 and classification accuracy of 86.9% with AUC of 92.1% (Sensitivity: 67.7%, specificity: 92.3%) over 5-fold cross-validation. We conclude that time-domain measures of NM alone can deliver comparable MCI to AD conversion prediction performance without leveraging more expensive and invasive counterparts such as MR imaging, PET scans, and CSF measures. Middle and low-income countries will benefit from such cheap and effective solutions greatly. PubDate: Tue, 18 Oct 2022 11:50:00 +000
Abstract: An electrocardiogram (ECG) uses electrodes to monitor the heart rhythm and identify minute electrical changes that occur with each beat. It is employed to investigate particular varieties of aberrant heart activity, such as arrhythmias and conduction problems. One of the most essential tools for detecting heart problems is the electrocardiogram (ECG). The majority of ECG records are still on paper. Manual ECG paper record analysis can be difficult and time-consuming. It is possible to digitally digitize these paper ECG recordings for automated analysis and diagnosis. In this paper, we proposed a system to digitize the ECG paper, automatically detecting R peaks, calculating the average heart rate, and sending SMS to the doctor via cloud in the event of detection of abnormality. The method of the system is uploading an ECG image, then dimensionality reduction, feature extraction in the form of digital signals, and saving it in a CSV file format using the MATLAB programming language. After that, the system retrieves the signals for further processing of the raw signals. We used the fast Fourier transform (FFT) algorithm to calculate R peaks and calculate the heart rate. If the heart rate is abnormal, the system sends SMS messages to doctors via a technology platform (Twilio) using the Python programming language. PubDate: Mon, 10 Oct 2022 11:20:02 +000
Abstract: Software failure such as software defect causes billion of dollar loss every year. Software failure also affects billion of people worldwide. Inadequate software testing can cause software failure. To predict the software defect, this study proposed a model consisting of feature selection and classifications. The correlation base method was used for feature selection, and radial base function neural network (RBF) was used for classification. Also, for testing the proposed system, fourteen NASA data sets were used including CM1, JM1, KC1, KC2, KC3, KC4, MC1, MC2, MW1, PC1, PC2, PC3, PC4, and PC5. The data set was divided using the well-known K-cross-validation methods which were performed to divide the data set for training and testing the RBF. The RBF were trained and tested before and after feature selections. Precision, recall, F-measure, and accuracy are four methods used to evaluate the performance of the proposed methods. The precision obtained for the fourteen data sets was CM1, 94.01%; JM1, 85.18%; KC1, 83.24%; KC2, 81.27%; KC3, 79.30%; KC4, 85.29%; MC1, 99.89%; MC2, 73.27%; MW1, 90.90%; PC1, 98.79%; PC2, 100%; PC3, 95.67%; PC4, 95.12%; and PC5, 80.89%. Recall was as follows: CM1, 95.78%; JM1, 87.89%; KC1, 86.24%; KC2, 83.82%; KC3, 82.10%; KC4, 86.28%; MC1, 100%; MC2, 76.67%; MW1, 92.09%; PC1, 99.98%; PC2, 100%; PC3, 96.23%; PC4, 95.17%; and PC5, 81.80%. F-measure was as follows: CM1, 0.95; JM1, 0.87; KC1, 0.83; KC2, 0.82; KC3, 0.85; KC4, 0.86; MC1, 0.99; MC2, 0.76; MW1, 0.95; PC1, 0.99; PC2, 0.99; PC3, 0.97; PC4, 0.95; and PC5, 0.80. The accuracy obtained was as follows: CM1, 93.99%; JM1, 84.87%; KC1, 83.25%; KC2, 79.11%; KC3, 78.25%; KC4, 83.18%; MC1, 99.01%; MC2, 70.18%; MW1, 88.90%; PC1, 98.99%; PC2, 99.80%; PC3, 94.11%; PC4, 94.4%; and PC5, 79.02%. The proposed method results were compared with the result obtained from different methods. The proposed model obtained better results than other methods for data set CM1, KC4, MC1, PC1, PC2, PC3, PC4, and PC5. PubDate: Mon, 26 Sep 2022 14:50:02 +000
Abstract: Ubiquitous computing (UC) is an advanced computing concept that makes services and computing available everywhere and anytime. In UC, data lies at the heart of all UC applications, and the key technologies that are required to make UC a reality are data and task management. In this context, retrieving data is influenced by the dynamic nature of these systems in addition to human and sensor failures. So the main problem is how to select the most appropriate service provider for retrieving data. Retrieving data is a complex issue that requires an extensive evaluation process and is one of the biggest challenges in UC. In addition, not every eventuality in these systems can be predicted due to their dynamic nature. As a result, there is a strong need to address the uncertainty in context data. In this paper, to assist users to efficiently select their most preferred service provider for retrieving data, a new fuzzy integrated multicriteria decision-making model, which meets quality of context (QoC) and quality of service (QoS) and satisfies user quality requirements and needs, is proposed. The proposed model is based on four stages. In the initial stage, the identification of evaluation criteria is performed due to the varying importance of the selected criteria. In the second stage, a fuzzy Analytical Hierarchy Process (FAHP) procedure is utilized to assign importance weights to each criterion. In the third stage, the fuzzy Technique for Order Preference by Similarity of an Ideal Solution (FTOPSIS) is used to evaluate and measure the performance of each alternative. Finally, sensitivity analysis is performed to check the robustness and the applicability of the proposed model. PubDate: Thu, 22 Sep 2022 06:50:01 +000
Abstract: Breast cancer disease is one of the most recorded cancers that lead to morbidity and maybe death among women around the world. Recent research statistics have exposed that one from 8 females in the USA and one from 10 females in Europe are contaminated by breast cancer. The challenge with this disease is how to develop a relaxed and fast diagnosing method. One of the attractive ways of early breast cancer diagnosis is based on the mammogram images analysis of the breast using a computer-aided diagnosing (CAD) tool. This paper firstly aimed to propose an efficient method for diagnosing tumors based on mammogram images of breasts using a machine learning approach. Secondly, this paper aimed to the development of a CAD software program for breast cancer diagnosing based on the proposed method in the first step. The followed step-by-step procedure of the proposed method is performed by passing the Mammographic Image Analysis Society (MIAS) through five steps of image preprocessing, image segmentation using seeded region growing (SRG) algorithm, feature extraction using different feature’s extraction classes, and important and effectiveness feature selection using the Sequential Forward Selection (SFS) technique, and finally, the Support Vector Machine (SVM) algorithm is used as a binary classifier in two classification levels. The first level classifier is used to categorize the given image as normal or abnormal while the second-level classifier is used for further classifying the abnormal image as either a malignant or benign cancer. The proposed method is studied and investigated in two phases: the training phase and the testing phase, with the MIAS dataset of mammogram images, using 70% and 30% ratios of dataset images for the training and testing sets, respectively. The practical implementation of the proposed method and the graphical user interface (GUI) CAD tool are carried out using MATLAB software. Experimental results of the proposed method have shown that the accuracy of the proposed method reached 100% in classifying images as normal and abnormal mammogram images while the classification accuracy for benign and malignant is equal to 87.1%. PubDate: Tue, 20 Sep 2022 06:35:03 +000
Abstract: Recently, educational institutions faced many challenges. One of these challenges is the huge amount of educational data that can be used to discover new insights that have a significant contribution to students, teachers, and administrators. Nowadays, researchers from numerous domains are very interested in increasing the quality of learning in educational institutions in order to improve student success and learning outcomes. Several studies have been made to predict student achievement at various levels. Most of the previous studies were focused on predicting student performance at graduation time or at the level of a specific course. The main objective of this paper is to highlight the recently published studies for predicting student academic performance in higher education. Moreover, this study aims to identify the most commonly used techniques for predicting the student's academic level. In addition, this study summarized the highest influential features used for predicting the student academic performance where identifying the most influential factors on student’s performance level will help the student as well as the policymakers and will give detailed insights into the problem. Finally, the results showed that the RF and ensemble model were the most accurate models as they outperformed other models in many previous studies. In addition, researchers in previous studies did not agree on whether the admission requirements have a strong relationship with students' achievement or not, indicating the need to address this issue. Moreover, it has been noticed that there are few studies which predict the student academic performance using students’ data in arts and humanities major. PubDate: Mon, 19 Sep 2022 16:05:02 +000
Abstract: The heart’s electrical activity is registered by an electrocardiogram (ECG), which consists of a wealth of pathological data on heart diseases such as arrhythmia. However, with increasing complexity and nonlinearity, direct observation of ECG signals and analysis is very tough. The highest accuracy of classification performance for machine learning approaches are 99.7 for neural network with wavelet scattering features extraction and 99.92 for SVM also with wavelet scattering features extraction. Through wavelet cascades with a neural network, the wavelet scattering transform can yield a translation invariant and deflection depictions of ECG signals. We suggested a new wavelet scattering transform-based method for automatically classifying three types of ECG heart diseases as follows: arrhythmia (ARR), congestive heart failure (CHF), and normal sinus rhythm (NSR). The bandwidth of the scaling function is used to critically downsample the wavelet scattering transform in time. As a result, each of the scattering paths has 16-time windows. Beat classification performance is classified by utilizing the MIT-BIH arrhythmia dataset. The suggested method is able to conduct high accuracy arrhythmia classification, with a 99.7% and 99.92% accuracy rate of the neural network (NN) and support vector machine (SVM), respectively, and will aid physicians in ECG explanation. PubDate: Mon, 19 Sep 2022 08:35:01 +000
Abstract: Automatic image caption generation is an intricate task of describing an image in natural language by gaining insights present in an image. Featuring facial expressions in the conventional image captioning system brings out new prospects to generate pertinent descriptions, revealing the emotional aspects of the image. The proposed work encapsulates the facial emotional features to produce more expressive captions similar to human-annotated ones with the help of Cross Stage Partial Dense Network (CSPDenseNet) and Self-attentive Bidirectional Long Short-Term Memory (BiLSTM) network. The encoding unit captures the facial expressions and dense image features using a Facial Expression Recognition (FER) model and CSPDense neural network, respectively. Further, the word embedding vectors of the ground truth image captions are created and learned using the Word2Vec embedding technique. Then, the extracted image feature vectors and word vectors are fused to form an encoding vector representing the rich image content. The decoding unit employs a self-attention mechanism encompassed with BiLSTM to create more descriptive and relevant captions in natural language. The Flickr11k dataset, a subset of the Flickr30k dataset is used to train, test, and evaluate the present model based on five benchmark image captioning metrics. They are BiLingual Evaluation Understudy (BLEU), Metric for Evaluation of Translation with Explicit Ordering (METEOR), Recall-Oriented Understudy for Gisting Evaluation (ROGUE), Consensus-based Image Description Evaluation (CIDEr), and Semantic Propositional Image Caption Evaluation (SPICE). The experimental analysis indicates that the proposed model enhances the quality of captions with 0.6012(BLEU-1), 0.3992(BLEU-2), 0.2703(BLEU-3), 0.1921(BLEU-4), 0.1932(METEOR), 0.2617(CIDEr), 0.4793(ROUGE-L), and 0.1260(SPICE) scores, respectively, using additive emotional characteristics and behavioral components of the objects present in the image. PubDate: Sat, 17 Sep 2022 03:20:02 +000
Abstract: Artificial intelligence has recently been used in FANET-based routing strategies for decision-making, which is a unique paradigm. For effective communication in flying vehicles that use routing protocols to accomplish tasks collectively, aerial vehicles are used in both civic and military applications. Aerial ad hoc networks are wirelessly connected, and designing routing schemes is difficult due to the rapid mobility. Ground base stations and satellites are frequently used to interconnect UAV ad hoc networks. This paper developed a novel routing protocol with a focus on ant behavior routing, which assists in end-to-end security. For the first time in flying networks, the column mobility model is used to evaluate the performance of routing protocols. While merging with aerial ad hoc networks, AI-based networking is a relatively new field. In simulation results, AntHocNet shows better results in comparison with other contemporary routing algorithms. Pheromone update process is used for data encryption in AntHocNet. This research study is performed on network simulator-2. PubDate: Fri, 16 Sep 2022 15:50:01 +000
Abstract: Currently, speech recognition datasets are increasingly available freely in various languages. However, speech recognition datasets in the Indonesian language are still challenging to obtain. Consequently, research focusing on speech recognition is challenging to carry out. This research creates Indonesian speech recognition datasets from YouTube channels with subtitles by validating all utterances of downloaded audio to improve the data quality. The quality of the dataset was evaluated using a deep neural network. The time delay neural network (TDNN) was used to build the acoustic model by applying the alignment data from the Gaussian mixture model-hidden Markov model (GMM-HMM). Data augmentation was used to increase the number of validated datasets and enhance the performance of the acoustic model. The results show that the acoustic model built using the validated datasets is better than the unvalidated datasets for all types of lexicons. Utilizing the four lexicon types and increasing the data through augmentation to train the acoustic models can lower the word error rate percentage in the GMM-HMM, TDNN factorization (TDNNF), and CNN-TDNNF-augmented models to 40.85%, 24.96%, and 19.03%, respectively. PubDate: Fri, 16 Sep 2022 10:05:02 +000
Abstract: One of the major challenges in developing various practical communication systems is reducing device complexity and development costs. In this study, a linear sparse array antenna design problem is addressed and a new approach for density taper element spacing by using the spacing coefficient algorithm is proposed. This method is a mathematical approach to obtain the distance between array elements by developing a spacing coefficient for each element to achieve radiation performances with a minimum number of antenna elements. The simulation and measurement results show a significant improvement in array performance compared to other sparse array design methods, such as the CDS sparse array method in our previous work. PubDate: Wed, 14 Sep 2022 13:05:01 +000
Abstract: Residential projects are described as complex, dynamic systems that are subject to uncertainty. Cost performance is a fundamental challenge. As a result, project managers must adequately identify risks that might lead to cost overruns in residential construction projects. Simulation is noticed to be a useful technique for dealing with these complications. Therefore, this study developed a hybrid dynamic approach to study the effect of different risks on the cost performance of construction projects. The proposed approach combines system dynamics (SD) and discrete event simulation (DES), which can take into consideration the dynamics of the project environment, which contains various continuous influencing factors as well as the construction operations. The developed hybrid model is validated through serial model structure tests and model behavior tests, with the aid of data collected from a real construction project used in the simulation process. Based on the simulation results, it is concluded that the proposed hybrid dynamic approach is helpful to enhance the process performance by permitting construction managers to identify possible process improvement areas that traditional methods may miss. PubDate: Mon, 05 Sep 2022 15:05:00 +000
Abstract: Satellite-based precipitation products, (SbPPs) have piqued the interest of a number of researchers as a reliable replacement for observed rainfall data which often have limited time spans and missing days. The SbPPs possess certain uncertainties, thus, they cannot be directly used without comparing against observed rainfall data prior to use. The Kelani river basin is Sri Lanka’s fourth longest river and the main source of water for almost 5 million people. Therefore, this research study aims to identify the potential of using SbPPs as a different method to measure rain besides using a rain gauge. Furthermore, the aim of the work is to examine the trends in precipitation products in the Kelani river basin. Three SbPPs, precipitation estimation using remotely sensed information using artificial neural networks (PERSIANN), PERSIANN-cloud classification system (CCS), and PERSIANN-climate data record (CDR) and ground observed rain gauge daily rainfall data at nine locations were used for the analysis. Four continuous evaluation indices, namely, root mean square error (RMSE), (percent bias) PBias, correlation coefficient (CC), and Nash‒Sutcliffe efficiency (NSE) were used to determine the accuracy by comparing against observed rainfall data. Four categorical indices including probability of detection (POD), false alarm ratio (FAR), critical success index (CSI), and proportional constant (PC) were used to evaluate the rainfall detection capability of SbPPs. Mann‒Kendall test and Sen’s slope estimator were used to identifying whether a trend was present while the magnitudes of these were calculated by Sen’s slope. PERSIANN-CDR performed well by showing better performance in both POD and CSI. When compared to observed rainfall data, the PERSIANN product had the lowest RMSE value, while all products indicated underestimations. The CC and NSE of all three products with observed rainfall data were also low. Mixed results were obtained for the trend analysis as well. The overall results showed that all three products are not a better choice for the chosen study area. PubDate: Wed, 31 Aug 2022 13:05:01 +000
Abstract: Program accreditation is important for determining whether or not a program or institution meets quality standards. It helps employers to evaluate the programs and qualifications of their graduates as well as to achieve its strategic goals and its continuous improvement plans. Preparing for accreditation requires extensive effort. One of the required documents is the program’s self-study report (SSR), which includes the PEO-SO map (which allocates the program’s educational objectives (PEOs) to student learning outcomes (SOs)). It influences program structure design, performance monitoring, assessment, and continuous improvement. Professionals in each academic engineering program have designed their PEO-SO maps in accordance with their experiences. The problem with the incorrect design of map design is that the SOs are either missing altogether or cannot be assigned to the correct PEOs. The objective of this work is to use a hybrid data mining approach to design the correct PEO-SO map. The proposed hybrid approach utilizes three different data mining techniques: classification to find the similarities between PEOs, crisp association rules to find the crisp rules for the PEO-SO map, and rough set association rules to find the coarse association rules for the PEO-SO map. The work collected 200 SSRs of accredited engineering programs by the ABET-EAC. The paper presents the different phases of the work, such as data collection and preprocessing, building of three data mining models (classification, crisp association rules, and rough set association rules), and analysis of the results and comparison with related work. The validation of the obtained results by different fifty specialists (from the academic engineering field) and their recommendations were also presented. The comparison with other related works proved the success of the proposed approach to discover the correct PEO-SO maps with higher performance. PubDate: Tue, 30 Aug 2022 12:50:01 +000
Abstract: We define soft Q-sets as soft sets whose soft closure and soft interior are commutative. We show that the soft complement, soft closure, and soft interior of a soft Q-set are all soft Q-sets. We show that a soft subset K of a given soft topological space is a soft Q-set if and only if K is a soft symmetric difference between a soft clopen set and a soft nowhere dense set. And as a corollary, the class of soft Q-sets contains simultaneously the classes of soft clopen sets and soft nowhere dense sets. Also, we prove that the class of soft Q-sets is closed under finite soft intersections and finite soft unions, and as a main result, we prove that the class of soft Q-sets forms a Boolean algebra. Furthermore, via soft Q-sets, we characterize soft sets whose soft boundaries and soft interiors are commutative. In addition, we investigate the correspondence between Q-sets in topological spaces and soft Q-sets in soft topological spaces. PubDate: Sun, 28 Aug 2022 13:05:00 +000
Abstract: Fog computing domain plays a prominent role in supporting time-delicate applications, which are associated with smart Internet of Things (IoT) services, like smart healthcare and smart city. However, cloud computing is a capable standard for IoT in data processing owing to the high latency restriction of the cloud, and it is incapable of satisfying needs for time-sensitive applications. The resource provisioning and allocation process in fog-cloud structure considers dynamic alternations in user necessities, and also restricted access resources in fog devices are more challenging. The global adoption of IoT-driven applications has led to the rise of fog computing structure, which permits perfect connection for mobile edge and cloud resources. The effectual scheduling of application tasks in fog environments is a challenging task because of resource heterogeneity, stochastic behaviours, network hierarchy, controlled resource abilities, and mobility elements in IoT. The deadline is the most significant challenge in the fog computing structure due to the dynamic variations in user requirement parameters. In this paper, Mayfly Taylor Optimisation Algorithm (MTOA) is developed for dynamic scheduling in the fog-cloud computing model. The developed MTOA-based Deep Q-Network (DQN) showed better performance with energy consumption, service level agreement (SLA), and computation cost of 0.0162, 0.0114, and 0.0855, respectively. PubDate: Sun, 28 Aug 2022 12:20:01 +000
Abstract: There are many alternative gas-fired combi boilers that can be used to heat residential homes. Evaluation and selection of gas-fired combi boilers for buildings is an intricate multi-criteria decision-making (MCDM) problem involving perhaps contradictory quantifiable and qualitative criteria. In this research, as the MCDM approach, hesitant fuzzy linguistic analytic hierarchy process (HF-AHP) and hesitant fuzzy linguistic “multiple objective optimization based on ratio analysis plus full multiplicative form (MULTIMOORA)” (HF-MULTIMOORA) are integrated to assess and rank combi boiler alternatives for buildings. First, with HF-AHP, fuzzy criteria weights are determined and then with HF-MULTIMOORA, boiler alternatives are ranked from best to worst. In this integrated HF-AHP-MULTIMOORA method, evaluations of decision-makers are combined with fuzzy envelope approach and then triangular fuzzy numbers are utilized. For comparison analysis, HF-AHP-TOPSIS method is also applied to the same problem. A case study in Turkey is presented where ten combi boiler alternatives are assessed based on fifteen criteria by five decision-makers. We have used various selection criteria for boilers ranging from maximum temperature, heating capacity up to environmental effects and decided on the best combi boiler for heating residential buildings in Turkey. PubDate: Thu, 25 Aug 2022 14:20:01 +000
Abstract: Deep learning techniques have recently demonstrated their ability to be applied in any field, including image processing, natural language processing, speech recognition, and many other real-world problem-solving applications. Human activity recognition (HAR), on the other hand, has become a popular research topic due to its wide range of applications. The researchers began working on the new ideas by combining the two emerging areas to solve HAR problems using deep learning. Recurrent neural networks (RNNs) in deep learning (DL) provide higher opportunity in recognizing the abnormal behavior of humans to avoid any kind of security issues. The present study proposed a deep network architecture based on one of the techniques of deep learning named as residual bidirectional long-term memory (LSTM). The new network is capable of avoiding gradient vanishing in both temporal and spatial dimensions with a view to increase the rate of recognition. To understand the complexity of activities recognition and classification, two LSTM models, basic model and the proposed model, were used. Later, a comparative analysis is performed to understand the efficiencies of the models during the classification of five human activities like abuse, arrest, arson, assault, and fighting images classification. The basic LSTM model has achieved a training accuracy of just 18% and testing accuracy of 21% with higher training and classification loss values. But the proposed LSTM model has outperformed the basic model while achieving 100% classification accuracy. Finally, the observations have proved that the proposed LSTM model is best suitable in recognizing and classifying the human activities well even for real-time videos. PubDate: Tue, 23 Aug 2022 11:50:05 +000
Abstract: Fog computing is becoming a dynamic and sought-after computing prototype for Internet of Things (IoT) application deployments. It works in conjunction with the cloud computing environment. Load balancing, which is employed by IoT applications when deciding, which fog or cloud computing nodes to use, is one of the most critical components for enhancing resource efficiency and avoiding problems like overloading or underloading. However, for IoT applications, ensuring that all CPU nodes are evenly distributed in terms of latency and energy utilization remains a challenge. To solve these issues, this work introduces Differential Grey Wolf (DGW) load balancing with stochastic Bellman deep reinforced resource optimization (DGW-SBDR) in fog situations. A Differential Evolution-based Grey Wolf Optimization algorithm based on load balancing has been developed for optimal resource management. The Grey Wolf Optimization algorithm, which employs differential evolution, assigns jobs to virtual machines based on user demands (VMs). In the event of an overutilized VM pool, a grey wolf optimization strategy based on differential evolution can detect both under and overutilized VMs, allowing for smooth transit between fogs. This step disables a number of virtual machines in order to reduce latency. In a Stochastic Gradient and Deep Reinforcement Learning-based Resource Allocation Model, a stochastic gradient bellman optimality function and Deep Reinforcement Learning are integrated for optimal resource allocation. According to the proposed method, QoS may be supplied to end-users by reducing energy consumption and better managing cache resources utilizing stochastic gradient bellman optimality. PubDate: Fri, 19 Aug 2022 02:50:00 +000
Abstract: This paper explores ear biometrics using a mixture of feature extraction techniques and classifies this feature vector using deep learning with convolutional neural network. This exploration of ear biometrics uses images from 2D facial profiles and facial images. The investigated feature techniques are Zernike Moments, local binary pattern, Gabor filter, and Haralick texture moments. The normalised feature vector is used to examine whether deep learning using convolutional neural network is better at identifying the ear than other commonly used machine learning techniques. The widely used machine learning techniques that were used to compare them are decision tree, naïve Bayes, K-nearest neighbors (KNN), and support vector machine (SVM). This paper proved that using a bag of feature techniques and the classification technique of deep learning using convolutional neural network was better than standard machine learning techniques. The result achieved by the deep learning using convolutional neural network was 92.00% average ear identification rate for both left and right ears. PubDate: Wed, 17 Aug 2022 08:05:01 +000
Open Access journal
[339 journals]
